Triple
T30369796
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SECAM |
E772517
|
entity |
| Predicate | firstRegularBroadcastsCountry |
P203763
|
FINISHED |
| Object | France |
E861
|
NE FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: France | Statement: [SECAM, firstRegularBroadcastsCountry, France]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstRegularBroadcastsCountry Context triple: [SECAM, firstRegularBroadcastsCountry, France]
-
A.
firstBroadcastInCountry
Indicates that a work (such as a program or broadcast) was first aired or transmitted in a specified country.
-
B.
firstRegularBroadcasts
chosen
Indicates that the subject is the entity that initiated or carried out the earliest recurring or scheduled broadcasts associated with the object.
-
C.
firstBroadcastFor
Indicates that one entity is the initial or earliest broadcast instance associated with another entity (such as a program, episode, or event).
-
D.
televisionDebutCountry
Indicates the country in which a person or work first appeared or was broadcast on television.
-
E.
firstBroadcastBy
Indicates that one entity is the original broadcaster or channel that first aired the other entity (such as a program, event, or content).
- F. None of above.
Provenance (4 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69f2248d71408190aec0d5c2001b1cff |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_6a01ed1790148190b08c1dba53de4371 |
completed | May 11, 2026, 2:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a2798a4e7c88190b230f90cca0d12ea |
completed | June 9, 2026, 4:37 a.m. |
| PD | Predicate disambiguation | batch_6a01e9c20798819085760b377dc7b3fa |
completed | May 11, 2026, 2:37 p.m. |
Created at: April 29, 2026, 7:59 p.m.